Yi Yang

A GPGPU compiler for memory optimization and parallelism management http://portal.acm.org/citation.cfm?id=1806596.1806606 This paper presents a optimizing compiler for GPGPU. The compiler gets naive kernels, and generates the kernels that optimized in memory coalescing, thread & thread-block merging and removing memory partition camping. This

Pete Keleher

TreadMarks: distributed shared memory on standard workstations and operating systems http://portal.acm.org/citation.cfm?id=1267084 TreadMarks is a DSM system that exploits Lazy Release Consistency Model and Lazy Diff Creation. Lazy Release Consistency postpone the propgation of modifications in distributed system until the time

Yunheung Paek

Simplification of array access patterns for compiler optimizations http://portal.acm.org/citation.cfm?id=277650.277664 Authors present a noble technique named LMAD(Linear Memory Access Descriptor). LMAD consists of stride/span pairs and base offset. Analyzing complex array access pattern could be simpler with LMAD. Thus, some compiler